Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5395
    Prev
    Next
    INDEX
    Explanations

    topics related to various forms of art and their societal impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íĹĮ
    -0.07
    ander
    -0.07
    gin
    -0.07
    rost
    -0.07
    intColor
    -0.07
    esto
    -0.07
    ÂŃi
    -0.06
    kü
    -0.06
    lide
    -0.06
    (UInt
    -0.06
    POSITIVE LOGITS
     ranging
    0.18
     whether
    0.18
     both
    0.16
    whether
    0.15
     various
    0.14
    Whether
    0.14
     Whether
    0.13
    åIJĦç§į
    0.13
    both
    0.13
     WHETHER
    0.13
    Activations Density 0.084%

    No Known Activations